#include "llvm/DebugInfo/Symbolize/MarkupFilter.h"
#include "llvm/ADT/None.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringSwitch.h"
#include "llvm/DebugInfo/DIContext.h"
#include "llvm/DebugInfo/Symbolize/Markup.h"
#include "llvm/DebugInfo/Symbolize/Symbolize.h"
#include "llvm/Debuginfod/Debuginfod.h"
#include "llvm/Demangle/Demangle.h"
#include "llvm/Object/ObjectFile.h"
#include "llvm/Support/Error.h"
#include "llvm/Support/Format.h"
#include "llvm/Support/FormatVariadic.h"
#include "llvm/Support/WithColor.h"
#include "llvm/Support/raw_ostream.h"
using namespace llvm;
using namespace llvm::symbolize;
MarkupFilter::MarkupFilter(raw_ostream &OS, LLVMSymbolizer &Symbolizer,
Optional<bool> ColorsEnabled)
: OS(OS), Symbolizer(Symbolizer),
ColorsEnabled(
ColorsEnabled.value_or(WithColor::defaultAutoDetectFunction()(OS))) {}
void MarkupFilter::filter(StringRef Line) {
this->Line = Line;
resetColor();
Parser.parseLine(Line);
SmallVector<MarkupNode> DeferredNodes;
while (Optional<MarkupNode> Node = Parser.nextNode()) {
if (tryContextualElement(*Node, DeferredNodes))
return;
DeferredNodes.push_back(*Node);
}
endAnyModuleInfoLine();
for (const MarkupNode &Node : DeferredNodes)
filterNode(Node);
}
void MarkupFilter::finish() {
Parser.flush();
while (Optional<MarkupNode> Node = Parser.nextNode())
filterNode(*Node);
endAnyModuleInfoLine();
resetColor();
Modules.clear();
MMaps.clear();
}
bool MarkupFilter::tryContextualElement(
const MarkupNode &Node, const SmallVector<MarkupNode> &DeferredNodes) {
if (tryMMap(Node, DeferredNodes))
return true;
if (tryReset(Node, DeferredNodes))
return true;
return tryModule(Node, DeferredNodes);
}
bool MarkupFilter::tryMMap(const MarkupNode &Node,
const SmallVector<MarkupNode> &DeferredNodes) {
if (Node.Tag != "mmap")
return false;
Optional<MMap> ParsedMMap = parseMMap(Node);
if (!ParsedMMap)
return true;
if (const MMap *M = getOverlappingMMap(*ParsedMMap)) {
WithColor::error(errs())
<< formatv("overlapping mmap: #{0:x} [{1:x}-{2:x}]\n", M->Mod->ID,
M->Addr, M->Addr + M->Size - 1);
reportLocation(Node.Fields[0].begin());
return true;
}
auto Res = MMaps.emplace(ParsedMMap->Addr, std::move(*ParsedMMap));
assert(Res.second && "Overlap check should ensure emplace succeeds.");
MMap &MMap = Res.first->second;
if (!MIL || MIL->Mod != MMap.Mod) {
endAnyModuleInfoLine();
for (const MarkupNode &Node : DeferredNodes)
filterNode(Node);
beginModuleInfoLine(MMap.Mod);
OS << "; adds";
}
MIL->MMaps.push_back(&MMap);
return true;
}
bool MarkupFilter::tryReset(const MarkupNode &Node,
const SmallVector<MarkupNode> &DeferredNodes) {
if (Node.Tag != "reset")
return false;
if (!checkNumFields(Node, 0))
return true;
if (!Modules.empty() || !MMaps.empty()) {
endAnyModuleInfoLine();
for (const MarkupNode &Node : DeferredNodes)
filterNode(Node);
highlight();
OS << "[[[reset]]]" << lineEnding();
restoreColor();
Modules.clear();
MMaps.clear();
}
return true;
}
bool MarkupFilter::tryModule(const MarkupNode &Node,
const SmallVector<MarkupNode> &DeferredNodes) {
if (Node.Tag != "module")
return false;
Optional<Module> ParsedModule = parseModule(Node);
if (!ParsedModule)
return true;
auto Res = Modules.try_emplace(
ParsedModule->ID, std::make_unique<Module>(std::move(*ParsedModule)));
if (!Res.second) {
WithColor::error(errs()) << "duplicate module ID\n";
reportLocation(Node.Fields[0].begin());
return true;
}
Module &Module = *Res.first->second;
endAnyModuleInfoLine();
for (const MarkupNode &Node : DeferredNodes)
filterNode(Node);
beginModuleInfoLine(&Module);
OS << "; BuildID=";
printValue(toHex(Module.BuildID, true));
return true;
}
void MarkupFilter::beginModuleInfoLine(const Module *M) {
highlight();
OS << "[[[ELF module";
printValue(formatv(" #{0:x} ", M->ID));
OS << '"';
printValue(M->Name);
OS << '"';
MIL = ModuleInfoLine{M};
}
void MarkupFilter::endAnyModuleInfoLine() {
if (!MIL)
return;
llvm::stable_sort(MIL->MMaps, [](const MMap *A, const MMap *B) {
return A->Addr < B->Addr;
});
for (const MMap *M : MIL->MMaps) {
OS << (M == MIL->MMaps.front() ? ' ' : ',');
OS << '[';
printValue(formatv("{0:x}", M->Addr));
OS << '-';
printValue(formatv("{0:x}", M->Addr + M->Size - 1));
OS << "](";
printValue(M->Mode);
OS << ')';
}
OS << "]]]" << lineEnding();
restoreColor();
MIL.reset();
}
void MarkupFilter::filterNode(const MarkupNode &Node) {
if (!checkTag(Node))
return;
if (tryPresentation(Node))
return;
if (trySGR(Node))
return;
OS << Node.Text;
}
bool MarkupFilter::tryPresentation(const MarkupNode &Node) {
if (trySymbol(Node))
return true;
if (tryPC(Node))
return true;
if (tryBackTrace(Node))
return true;
return tryData(Node);
}
bool MarkupFilter::trySymbol(const MarkupNode &Node) {
if (Node.Tag != "symbol")
return false;
if (!checkNumFields(Node, 1))
return true;
highlight();
OS << llvm::demangle(Node.Fields.front().str());
restoreColor();
return true;
}
bool MarkupFilter::tryPC(const MarkupNode &Node) {
if (Node.Tag != "pc")
return false;
if (!checkNumFieldsAtLeast(Node, 1))
return true;
if (!checkNumFieldsAtMost(Node, 2))
return true;
Optional<uint64_t> Addr = parseAddr(Node.Fields[0]);
if (!Addr)
return true;
PCType Type = PCType::PreciseCode;
if (Node.Fields.size() == 2) {
Optional<PCType> ParsedType = parsePCType(Node.Fields[1]);
if (!ParsedType)
return true;
Type = *ParsedType;
}
*Addr = adjustAddr(*Addr, Type);
const MMap *MMap = getContainingMMap(*Addr);
if (!MMap) {
WithColor::error() << "no mmap covers address\n";
reportLocation(Node.Fields[0].begin());
printRawElement(Node);
return true;
}
Expected<DILineInfo> LI = Symbolizer.symbolizeCode(
MMap->Mod->BuildID, {MMap->getModuleRelativeAddr(*Addr)});
if (!LI) {
WithColor::defaultErrorHandler(LI.takeError());
printRawElement(Node);
return true;
}
if (!*LI) {
printRawElement(Node);
return true;
}
highlight();
printValue(LI->FunctionName);
OS << '[';
printValue(LI->FileName);
OS << ':';
printValue(Twine(LI->Line));
OS << ']';
restoreColor();
return true;
}
bool MarkupFilter::tryBackTrace(const MarkupNode &Node) {
if (Node.Tag != "bt")
return false;
if (!checkNumFieldsAtLeast(Node, 2))
return true;
if (!checkNumFieldsAtMost(Node, 3))
return true;
Optional<uint64_t> FrameNumber = parseFrameNumber(Node.Fields[0]);
if (!FrameNumber)
return true;
Optional<uint64_t> Addr = parseAddr(Node.Fields[1]);
if (!Addr)
return true;
PCType Type = PCType::ReturnAddress;
if (Node.Fields.size() == 3) {
Optional<PCType> ParsedType = parsePCType(Node.Fields[2]);
if (!ParsedType)
return true;
Type = *ParsedType;
}
*Addr = adjustAddr(*Addr, Type);
const MMap *MMap = getContainingMMap(*Addr);
if (!MMap) {
WithColor::error() << "no mmap covers address\n";
reportLocation(Node.Fields[0].begin());
printRawElement(Node);
return true;
}
uint64_t MRA = MMap->getModuleRelativeAddr(*Addr);
Expected<DIInliningInfo> II =
Symbolizer.symbolizeInlinedCode(MMap->Mod->BuildID, {MRA});
if (!II) {
WithColor::defaultErrorHandler(II.takeError());
printRawElement(Node);
return true;
}
highlight();
for (unsigned I = 0, E = II->getNumberOfFrames(); I != E; ++I) {
auto Header = formatv("{0, +6}", formatv("#{0}", FrameNumber)).sstr<16>();
size_t NumberIdx = Header.find("#") + 1;
OS << Header.substr(0, NumberIdx);
printValue(Header.substr(NumberIdx));
if (I == E - 1) {
OS << " ";
} else {
OS << '.';
printValue(formatv("{0, -2}", I + 1));
}
printValue(formatv(" {0:x16} ", *Addr));
DILineInfo LI = II->getFrame(I);
if (LI) {
printValue(LI.FunctionName);
OS << ' ';
printValue(LI.FileName);
OS << ':';
printValue(Twine(LI.Line));
OS << ':';
printValue(Twine(LI.Column));
OS << ' ';
}
OS << '(';
printValue(MMap->Mod->Name);
OS << "+";
printValue(formatv("{0:x}", MRA));
OS << ')';
if (I != E - 1)
OS << lineEnding();
}
restoreColor();
return true;
}
bool MarkupFilter::tryData(const MarkupNode &Node) {
if (Node.Tag != "data")
return false;
if (!checkNumFields(Node, 1))
return true;
Optional<uint64_t> Addr = parseAddr(Node.Fields[0]);
if (!Addr)
return true;
const MMap *MMap = getContainingMMap(*Addr);
if (!MMap) {
WithColor::error() << "no mmap covers address\n";
reportLocation(Node.Fields[0].begin());
printRawElement(Node);
return true;
}
Expected<DIGlobal> Symbol = Symbolizer.symbolizeData(
MMap->Mod->BuildID, {MMap->getModuleRelativeAddr(*Addr)});
if (!Symbol) {
WithColor::defaultErrorHandler(Symbol.takeError());
printRawElement(Node);
return true;
}
highlight();
OS << Symbol->Name;
restoreColor();
return true;
}
bool MarkupFilter::trySGR(const MarkupNode &Node) {
if (Node.Text == "\033[0m") {
resetColor();
return true;
}
if (Node.Text == "\033[1m") {
Bold = true;
if (ColorsEnabled)
OS.changeColor(raw_ostream::Colors::SAVEDCOLOR, Bold);
return true;
}
auto SGRColor = StringSwitch<Optional<raw_ostream::Colors>>(Node.Text)
.Case("\033[30m", raw_ostream::Colors::BLACK)
.Case("\033[31m", raw_ostream::Colors::RED)
.Case("\033[32m", raw_ostream::Colors::GREEN)
.Case("\033[33m", raw_ostream::Colors::YELLOW)
.Case("\033[34m", raw_ostream::Colors::BLUE)
.Case("\033[35m", raw_ostream::Colors::MAGENTA)
.Case("\033[36m", raw_ostream::Colors::CYAN)
.Case("\033[37m", raw_ostream::Colors::WHITE)
.Default(llvm::None);
if (SGRColor) {
Color = *SGRColor;
if (ColorsEnabled)
OS.changeColor(*Color);
return true;
}
return false;
}
void MarkupFilter::highlight() {
if (!ColorsEnabled)
return;
OS.changeColor(Color == raw_ostream::Colors::BLUE ? raw_ostream::Colors::CYAN
: raw_ostream::Colors::BLUE,
Bold);
}
void MarkupFilter::highlightValue() {
if (!ColorsEnabled)
return;
OS.changeColor(raw_ostream::Colors::GREEN, Bold);
}
void MarkupFilter::restoreColor() {
if (!ColorsEnabled)
return;
if (Color) {
OS.changeColor(*Color, Bold);
} else {
OS.resetColor();
if (Bold)
OS.changeColor(raw_ostream::Colors::SAVEDCOLOR, Bold);
}
}
void MarkupFilter::resetColor() {
if (!Color && !Bold)
return;
Color.reset();
Bold = false;
if (ColorsEnabled)
OS.resetColor();
}
void MarkupFilter::printRawElement(const MarkupNode &Element) {
highlight();
OS << "[[[";
printValue(Element.Tag);
for (StringRef Field : Element.Fields) {
OS << ':';
printValue(Field);
}
OS << "]]]";
restoreColor();
}
void MarkupFilter::printValue(Twine Value) {
highlightValue();
OS << Value;
highlight();
}
#define ASSIGN_OR_RETURN_NONE(TYPE, NAME, EXPR) \
auto NAME##Opt = (EXPR); \
if (!NAME##Opt) \
return None; \
TYPE NAME = std::move(*NAME##Opt)
Optional<MarkupFilter::Module>
MarkupFilter::parseModule(const MarkupNode &Element) const {
if (!checkNumFieldsAtLeast(Element, 3))
return None;
ASSIGN_OR_RETURN_NONE(uint64_t, ID, parseModuleID(Element.Fields[0]));
StringRef Name = Element.Fields[1];
StringRef Type = Element.Fields[2];
if (Type != "elf") {
WithColor::error() << "unknown module type\n";
reportLocation(Type.begin());
return None;
}
if (!checkNumFields(Element, 4))
return None;
ASSIGN_OR_RETURN_NONE(SmallVector<uint8_t>, BuildID,
parseBuildID(Element.Fields[3]));
return Module{ID, Name.str(), std::move(BuildID)};
}
Optional<MarkupFilter::MMap>
MarkupFilter::parseMMap(const MarkupNode &Element) const {
if (!checkNumFieldsAtLeast(Element, 3))
return None;
ASSIGN_OR_RETURN_NONE(uint64_t, Addr, parseAddr(Element.Fields[0]));
ASSIGN_OR_RETURN_NONE(uint64_t, Size, parseSize(Element.Fields[1]));
StringRef Type = Element.Fields[2];
if (Type != "load") {
WithColor::error() << "unknown mmap type\n";
reportLocation(Type.begin());
return None;
}
if (!checkNumFields(Element, 6))
return None;
ASSIGN_OR_RETURN_NONE(uint64_t, ID, parseModuleID(Element.Fields[3]));
ASSIGN_OR_RETURN_NONE(std::string, Mode, parseMode(Element.Fields[4]));
auto It = Modules.find(ID);
if (It == Modules.end()) {
WithColor::error() << "unknown module ID\n";
reportLocation(Element.Fields[3].begin());
return None;
}
ASSIGN_OR_RETURN_NONE(uint64_t, ModuleRelativeAddr,
parseAddr(Element.Fields[5]));
return MMap{Addr, Size, It->second.get(), std::move(Mode),
ModuleRelativeAddr};
}
Optional<uint64_t> MarkupFilter::parseAddr(StringRef Str) const {
if (Str.empty()) {
reportTypeError(Str, "address");
return None;
}
if (all_of(Str, [](char C) { return C == '0'; }))
return 0;
if (!Str.startswith("0x")) {
reportTypeError(Str, "address");
return None;
}
uint64_t Addr;
if (Str.drop_front(2).getAsInteger(16, Addr)) {
reportTypeError(Str, "address");
return None;
}
return Addr;
}
Optional<uint64_t> MarkupFilter::parseModuleID(StringRef Str) const {
uint64_t ID;
if (Str.getAsInteger(0, ID)) {
reportTypeError(Str, "module ID");
return None;
}
return ID;
}
Optional<uint64_t> MarkupFilter::parseSize(StringRef Str) const {
uint64_t ID;
if (Str.getAsInteger(0, ID)) {
reportTypeError(Str, "size");
return None;
}
return ID;
}
Optional<uint64_t> MarkupFilter::parseFrameNumber(StringRef Str) const {
uint64_t ID;
if (Str.getAsInteger(10, ID)) {
reportTypeError(Str, "frame number");
return None;
}
return ID;
}
Optional<SmallVector<uint8_t>> MarkupFilter::parseBuildID(StringRef Str) const {
std::string Bytes;
if (Str.empty() || Str.size() % 2 || !tryGetFromHex(Str, Bytes)) {
reportTypeError(Str, "build ID");
return None;
}
ArrayRef<uint8_t> BuildID(reinterpret_cast<const uint8_t *>(Bytes.data()),
Bytes.size());
return SmallVector<uint8_t>(BuildID.begin(), BuildID.end());
}
Optional<std::string> MarkupFilter::parseMode(StringRef Str) const {
if (Str.empty()) {
reportTypeError(Str, "mode");
return None;
}
StringRef Remainder = Str;
if (!Remainder.empty() && tolower(Remainder.front()) == 'r')
Remainder = Remainder.drop_front();
if (!Remainder.empty() && tolower(Remainder.front()) == 'w')
Remainder = Remainder.drop_front();
if (!Remainder.empty() && tolower(Remainder.front()) == 'x')
Remainder = Remainder.drop_front();
if (!Remainder.empty()) {
reportTypeError(Str, "mode");
return None;
}
return Str.lower();
}
Optional<MarkupFilter::PCType> MarkupFilter::parsePCType(StringRef Str) const {
Optional<MarkupFilter::PCType> Type =
StringSwitch<Optional<MarkupFilter::PCType>>(Str)
.Case("ra", MarkupFilter::PCType::ReturnAddress)
.Case("pc", MarkupFilter::PCType::PreciseCode)
.Default(None);
if (!Type)
reportTypeError(Str, "PC type");
return Type;
}
bool MarkupFilter::checkTag(const MarkupNode &Node) const {
if (any_of(Node.Tag, [](char C) { return C < 'a' || C > 'z'; })) {
WithColor::error(errs()) << "tags must be all lowercase characters\n";
reportLocation(Node.Tag.begin());
return false;
}
return true;
}
bool MarkupFilter::checkNumFields(const MarkupNode &Element,
size_t Size) const {
if (Element.Fields.size() != Size) {
WithColor::error(errs()) << "expected " << Size << " field(s); found "
<< Element.Fields.size() << "\n";
reportLocation(Element.Tag.end());
return false;
}
return true;
}
bool MarkupFilter::checkNumFieldsAtLeast(const MarkupNode &Element,
size_t Size) const {
if (Element.Fields.size() < Size) {
WithColor::error(errs())
<< "expected at least " << Size << " field(s); found "
<< Element.Fields.size() << "\n";
reportLocation(Element.Tag.end());
return false;
}
return true;
}
bool MarkupFilter::checkNumFieldsAtMost(const MarkupNode &Element,
size_t Size) const {
if (Element.Fields.size() > Size) {
WithColor::error(errs())
<< "expected at most " << Size << " field(s); found "
<< Element.Fields.size() << "\n";
reportLocation(Element.Tag.end());
return false;
}
return true;
}
void MarkupFilter::reportTypeError(StringRef Str, StringRef TypeName) const {
WithColor::error(errs()) << "expected " << TypeName << "; found '" << Str
<< "'\n";
reportLocation(Str.begin());
}
void MarkupFilter::reportLocation(StringRef::iterator Loc) const {
errs() << Line;
WithColor(errs().indent(Loc - Line.begin()), HighlightColor::String) << '^';
errs() << '\n';
}
const MarkupFilter::MMap *
MarkupFilter::getOverlappingMMap(const MMap &Map) const {
auto I = MMaps.upper_bound(Map.Addr);
if (I != MMaps.end() && Map.contains(I->second.Addr))
return &I->second;
if (I != MMaps.begin()) {
--I;
if (I->second.contains(Map.Addr))
return &I->second;
}
return nullptr;
}
const MarkupFilter::MMap *MarkupFilter::getContainingMMap(uint64_t Addr) const {
auto I = MMaps.lower_bound(Addr);
if (I != MMaps.end() && I->second.contains(Addr))
return &I->second;
if (I == MMaps.begin())
return nullptr;
--I;
return I->second.contains(Addr) ? &I->second : nullptr;
}
uint64_t MarkupFilter::adjustAddr(uint64_t Addr, PCType Type) const {
return Type == MarkupFilter::PCType::ReturnAddress ? Addr - 1 : Addr;
}
StringRef MarkupFilter::lineEnding() const {
return Line.endswith("\r\n") ? "\r\n" : "\n";
}
bool MarkupFilter::MMap::contains(uint64_t Addr) const {
return this->Addr <= Addr && Addr < this->Addr + Size;
}
uint64_t MarkupFilter::MMap::getModuleRelativeAddr(uint64_t Addr) const {
return Addr - this->Addr + ModuleRelativeAddr;
}